Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Version

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shifting
    -0.08
     appalling
    -0.07
    (Size
    -0.07
     Engine
    -0.07
     phủ
    -0.07
     alternating
    -0.07
    CustomAttributes
    -0.07
    厚
    -0.07
     aust
    -0.06
    Set
    -0.06
    POSITIVE LOGITS
    iedy
    0.06
     قادر
    0.06
    一种
    0.06
    gm
    0.06
    		
↵		
↵
    0.06
    bis
    0.06
     jasmine
    0.06
    _DESCRIPTOR
    0.05
     myslí
    0.05
     GLint
    0.05
    Act Density 0.001%

    No Known Activations